_ Git - youtube-dl/blob - youtube_dl/extractor/bitchute.py

   1 # coding: utf-8
   2 from __future__ import unicode_literals
   3
   4 import itertools
   5 import re
   6
   7 from .common import InfoExtractor
   8 from ..utils import urlencode_postdata
   9
  10
  11 class BitChuteIE(InfoExtractor):
  12     _VALID_URL = r'https?://(?:www\.)?bitchute\.com/(?:video|embed|torrent/[^/]+)/(?P<id>[^/?#&]+)'
  13     _TESTS = [{
  14         'url': 'https://www.bitchute.com/video/szoMrox2JEI/',
  15         'md5': '66c4a70e6bfc40dcb6be3eb1d74939eb',
  16         'info_dict': {
  17             'id': 'szoMrox2JEI',
  18             'ext': 'mp4',
  19             'title': 'Fuck bitches get money',
  20             'description': 'md5:3f21f6fb5b1d17c3dee9cf6b5fe60b3a',
  21             'thumbnail': r're:^https?://.*\.jpg$',
  22             'uploader': 'Victoria X Rave',
  23         },
  24     }, {
  25         'url': 'https://www.bitchute.com/embed/lbb5G1hjPhw/',
  26         'only_matching': True,
  27     }, {
  28         'url': 'https://www.bitchute.com/torrent/Zee5BE49045h/szoMrox2JEI.webtorrent',
  29         'only_matching': True,
  30     }]
  31
  32     def _real_extract(self, url):
  33         video_id = self._match_id(url)
  34
  35         webpage = self._download_webpage(
  36             'https://www.bitchute.com/video/%s' % video_id, video_id, headers={
  37                 'User-Agent': 'Mozilla/5.0 (Macintosh; Intel Mac OS X 10_14_0) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/69.0.3497.57 Safari/537.36',
  38             })
  39
  40         title = self._html_search_regex(
  41             (r'<[^>]+\bid=["\']video-title[^>]+>([^<]+)', r'<title>([^<]+)'),
  42             webpage, 'title', default=None) or self._html_search_meta(
  43             'description', webpage, 'title',
  44             default=None) or self._og_search_description(webpage)
  45
  46         formats = [
  47             {'url': mobj.group('url')}
  48             for mobj in re.finditer(
  49                 r'addWebSeed\s*\(\s*(["\'])(?P<url>(?:(?!\1).)+)\1', webpage)]
  50         self._sort_formats(formats)
  51
  52         description = self._html_search_regex(
  53             r'(?s)<div\b[^>]+\bclass=["\']full hidden[^>]+>(.+?)</div>',
  54             webpage, 'description', fatal=False)
  55         thumbnail = self._og_search_thumbnail(
  56             webpage, default=None) or self._html_search_meta(
  57             'twitter:image:src', webpage, 'thumbnail')
  58         uploader = self._html_search_regex(
  59             r'(?s)<p\b[^>]+\bclass=["\']video-author[^>]+>(.+?)</p>', webpage,
  60             'uploader', fatal=False)
  61
  62         return {
  63             'id': video_id,
  64             'title': title,
  65             'description': description,
  66             'thumbnail': thumbnail,
  67             'uploader': uploader,
  68             'formats': formats,
  69         }
  70
  71
  72 class BitChuteChannelIE(InfoExtractor):
  73     _VALID_URL = r'https?://(?:www\.)?bitchute\.com/channel/(?P<id>[^/?#&]+)'
  74     _TEST = {
  75         'url': 'https://www.bitchute.com/channel/victoriaxrave/',
  76         'playlist_mincount': 185,
  77         'info_dict': {
  78             'id': 'victoriaxrave',
  79         },
  80     }
  81
  82     _TOKEN = 'zyG6tQcGPE5swyAEFLqKUwMuMMuF6IO2DZ6ZDQjGfsL0e4dcTLwqkTTul05Jdve7'
  83
  84     def _entries(self, channel_id):
  85         channel_url = 'https://www.bitchute.com/channel/%s/' % channel_id
  86         offset = 0
  87         for page_num in itertools.count(1):
  88             data = self._download_json(
  89                 '%sextend/' % channel_url, channel_id,
  90                 'Downloading channel page %d' % page_num,
  91                 data=urlencode_postdata({
  92                     'csrfmiddlewaretoken': self._TOKEN,
  93                     'name': '',
  94                     'offset': offset,
  95                 }), headers={
  96                     'Content-Type': 'application/x-www-form-urlencoded; charset=UTF-8',
  97                     'Referer': channel_url,
  98                     'X-Requested-With': 'XMLHttpRequest',
  99                     'Cookie': 'csrftoken=%s' % self._TOKEN,
 100                 })
 101             if data.get('success') is False:
 102                 break
 103             html = data.get('html')
 104             if not html:
 105                 break
 106             video_ids = re.findall(
 107                 r'class=["\']channel-videos-image-container[^>]+>\s*<a\b[^>]+\bhref=["\']/video/([^"\'/]+)',
 108                 html)
 109             if not video_ids:
 110                 break
 111             offset += len(video_ids)
 112             for video_id in video_ids:
 113                 yield self.url_result(
 114                     'https://www.bitchute.com/video/%s' % video_id,
 115                     ie=BitChuteIE.ie_key(), video_id=video_id)
 116
 117     def _real_extract(self, url):
 118         channel_id = self._match_id(url)
 119         return self.playlist_result(
 120             self._entries(channel_id), playlist_id=channel_id)